Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2023

Abstract

Current math word problem (MWP) solvers are usually Seq2Seq models trained by the (one-problem; one-solution) pairs, each of which is made of a problem description and a solution showing reasoning flow to get the correct answer. However, one MWP problem naturally has multiple solution equations. The training of an MWP solver with (one-problem; one-solution) pairs excludes other correct solutions, and thus limits the generalizability of the MWP solver. One feasible solution to this limitation is to augment multiple solutions to a given problem. However, it is difficult to collect diverse and accurate augment solutions through human efforts. In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator. The buffer includes solutions generated by an MWP solver to encourage the training data diversity. The discriminator controls the quality of buffered solutions to participate in training. Our framework is flexibly applicable to a wide setting of fully, semi-weakly and weakly supervised training for all Seq2Seq MWP solvers. We conduct extensive experiments on a benchmark dataset Math23k and a new dataset named Weak12k, and show that our framework improves the performance of various MWP solvers under different settings by generating correct and diverse solutions.

Keywords

Question Answering, multiple solution equations, Argumentation, problem description, training framework

Discipline

Artificial Intelligence and Robotics | Mathematics | Theory and Algorithms

Publication

Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, Washington, February 7-14

Volume

37

First Page

13183

Last Page

13191

ISBN

9781577358800

Identifier

10.1609/aaai.v37i11.26548

Publisher

AAAI Press

City or Country

Washington

Additional URL

https://doi.org/10.1609/aaai.v37i11.26548

Download

Share

COinS